plot.Predict(rms)
plot.Predict()所属R语言包：rms
Plot Effects of Variables Estimated by a Regression Model Fit
图估计的回归模型拟合效果的变量
译者：生物统计家园网 机器人LoveR
描述----------Description----------
Uses lattice graphics to plot the effect of one or two predictors on the linear predictor or X beta scale, or on some transformation of that scale. The first argument specifies the result of the Predict function. The predictor is always plotted in its original coding. plot.Predict uses the xYplot function unless formula is omitted and the x-axis variable is a factor, in which case it reverses the x- and y-axes and uses the Dotplot function.
使用lattice图形绘制的效果中的一个或两个预测变量的线性预测或X公测规模上，或在该尺度一些改造。第一个参数指定的结果Predict功能。预测器总是绘制在其原始的编码上。 plot.Predict使用xYplot函数，除非formula被省略，并且在x轴的变量是一个因素，在这种情况下，它的x-轴和y-轴反转，并使用Dotplot 函数。
If data is given, a rug plot is drawn showing the location/density of data values for the x-axis variable. If there is a groups (superposition) variable that generated separate curves, the data density specific to each class of points is shown. This assumes that the second variable was a factor variable. The rug plots are drawn by scat1d. When the same predictor is used on all x-axes, and multiple panels are drawn, you can use subdata to specify an expression to subset according to other criteria in addition.
如果data，地毯图绘制的位置图/密度x-轴变量的数据值。如果有一个groups（叠加）变量，产生独立的曲线，每个类的点的数据密度的具体示出。这是假定第二个变量是一个因素变量。地毯图绘制scat1d。所有的x-轴使用相同的预测时，得出多个面板，你可以使用subdata根据其他标准，除了指定表达式的子集。
To plot effects instead of estimates (e.g., treatment differences as a function of interacting factors) see contrast.rms and summary.rms.
要绘制的效果，而不是估计（例如，待遇上的差别相互作用的因素的函数）contrast.rms和summary.rms。
pantext creates a lattice panel function for including text such as that produced by print.anova.rms inside a panel or in a base graphic.
pantext创建一个lattice面板功能，包括文字，如产生print.anova.rms在面板中或在基本图形。
用法----------Usage----------
## S3 method for class 'Predict'
plot(x, formula, groups=NULL,
cond=NULL, varypred=FALSE, subset,
xlim, ylim, xlab, ylab,
data=NULL, subdata, col.fill=gray(seq(.95, .75, length=5)),
adj.subtitle, cex.adj, cex.axis, perim=NULL, digits=4, nlevels=3,
nlines=FALSE, addpanel, scat1d.opts=list(frac=0.025, lwd=0.3), ...)
pantext(object, x, y, cex=.5, adj=0, fontfamily="Courier", lattice=TRUE)
参数----------Arguments----------
参数：x
a data frame created by Predict, or for pantext the x-coordinate for text
数据框创建的Predict或pantextx坐标的文本
参数：formula
the right hand side of a lattice formula reference variables in data frame x. You may not specify formula if you varied multiple predictors separately when calling Predict. Otherwise, when formula is not given, plot.Predict constructs one from information in x.
的右手侧的一个lattice式引用变量在数据框x。您可能没有指定formula“”如果你改变多个预测分别时调用Predict。否则，当formula不plot.Predict建构一个从信息中x。
参数：groups
an optional name of one of the variables in x that is to be used as a grouping (superpositioning) variable. Note that groups does not contain the groups data as is customary in lattice; it is only a single character string specifying the name of the grouping variable.
一个可选的名字中的变量之一x是被用来作为一个分组（superpositioning）变量。请注意，groups不包含的组数据作为习惯在lattice;它是只有一个单一的分组变量指定的名称的字符串。
参数：cond
when plotting effects of different predictors, cond is a character string that specifies a single variable name in x that can be used to form panels. Only applies if using rbind to combine several Predict results.
绘图时不同预测的影响，cond是一个字符串，它指定了一个单独的变量名，x，可用于形成面板。仅适用于使用rbind结合几个Predict结果。
参数：varypred
set to TRUE if x is the result of passing multiple Predict results, that represent different predictors, to rbind.Predict. This will cause the .set. variable created by rbind to be copied to the .predictor. variable.
设置成TRUE如果x是结果通过多个Predict结果，代表不同的预测，rbind.Predict的。“这将导致.set.变量创建的rbind.predictor.变量被复制到。
参数：subset
a subsetting expression for restricting the rows of x that are used in plotting. For example, predictions may have been requested for males and females but one wants to plot only females.
一个子集用于限制x中所使用的标绘的行中的表达。例如，预测可能会被要求为男性和女性，但要绘制唯一的女性。
参数：xlim
This parameter is seldom used, as limits are usually controlled with Predict. One reason to use xlim is to plot a factor variable on the x-axis that was created with the cut2 function with the levels.mean option, with val.lev=TRUE specified to plot.Predict. In this case you may want the axis to have the range of the original variable values given to cut2 rather than the range of the means within quantile groups.
此参数很少使用，限制控制Predict。使用的原因之一xlim是绘制一个factor变量x轴的创建cut2功能的levels.mean选项的，与val.lev=TRUE指定的plot.Predict。在这种情况下，您可能想要轴有原始的变量值给定的范围内cut2，而不是位数组的范围内的手段。
参数：ylim
Range for plotting on response variable axis. Computed by default.
图对响应变量轴的范围。默认情况下计算的。
参数：xlab
Label for x-axis. Default is one given to asis, rcs, etc., which may have been the "label" attribute of the variable.
x轴的标签。默认值是一个给定的asis, rcs，等，它可能已被"label"属性的变量。
参数：ylab
Label for y-axis. If fun is not given, default is "log Odds" for lrm, "log Relative Hazard" for cph, name of the response variable for ols, TRUE or log(TRUE) for psm, or "X * Beta" otherwise.
y轴的标签。 fun如果没有给出，默认是"log Odds"lrm，"log Relative Hazard"cph，响应变量的名称为ols，TRUE或log(TRUE)psm或"X * Beta"否则。
参数：data
a data frame containing the original raw data on which the regression model were based, or at least containing the x-axis and grouping variable. If data is present and contains the needed variables, the original data are added to the graph in the form of a rug plot using scat1d.
一个数据框，包含在其上的原始数据的回归模型为基础，或至少含有x-轴和分组变量。如果data是包含了所需的变量，原始数据将被添加到图中使用scat1d的形式的地毯图的。
参数：subdata
if data is specified, an expression to be evaluated in the data environment that evaluates to a logical vector specifying which observations in data to keep. This will be intersected with the criterion for the groups variable. Example: if conditioning on two paneling variables using |a*b you can specify subdata=b==levels(b)[which.packet()[2]], where the 2 comes from the fact that b was listed second after the vertical bar (this assumes b is a factor in data. Another example: subdata=sex==c('male','female')[current.row()].
如果data指定的表达式的求值在data环境，计算结果为逻辑向量，观测data保持。这将是相交的groups变量的标准。例：如果空调的两个镶板变量|a*b，“你可以指定subdata=b==levels(b)[which.packet()[2]]，其中2b列出的第二个后竖线（这是假设的事实b是factor中data。又如：subdata=sex==c('male','female')[current.row()]。
参数：col.fill
a vector of colors used to fill confidence bands for successive superposed groups. Default is inceasingly dark gray scale.
一个向量使用的颜色，以填补置信区间为连续叠加的群体。默认值是暗灰度inceasingly。
参数：adj.subtitle
Set to FALSE to suppress subtitling the graph with the list of settings of non-graphed adjustment values.
设置FALSE抑制字幕列表中设置非绘制的调整值图，。
参数：cex.adj
cex parameter for size of adjustment settings in subtitles. Default is 0.75 times par("cex").
cex参数调整设置字幕的大小。默认值是0.75倍par("cex")。
参数：cex.axis
cex parameter for x-axis tick labels
cex参数x轴刻度标签
参数：perim
perim specifies a function having two arguments. The first is the vector of values of the first variable that is about to be plotted on the x-axis. The second argument is the single value of the variable representing different curves, for the current curve being plotted. The function's returned value must be a logical vector whose length is the same as that of the first argument, with values TRUE if the corresponding point should be plotted for the current curve, FALSE otherwise. See one of the latter examples.
perim指定一个函数有两个参数。首先是大约是被绘制在x-轴的第一变量的值的矢量。第二个参数是单个值的变量，代表不同的曲线，所绘制的曲线。该函数的返回值必须是一个逻辑向量，其长度是一样的第一个参数的值TRUE，如果相应的点绘制的曲线，FALSE否则。参见后者的例子之一。
参数：digits
Controls how numeric variables used for panel labels are formatted. The default is 4 significant digits.
控制面板标签所使用的数值变量的格式化。默认值是4显著的数字。
参数：nlevels
when groups and formula are not specified, if any panel variable has nlevels or fewer values, that variable is converted to a groups (superpositioning) variable. Set nlevels=0 to prevent this behavior. For other situations, a numeric x-axis variable with nlevels or fewer unique values will cause a dot plot to be drawn instead of an x-y plot.
当groups和formula不指定任何面板变量，如果有nlevels或更少的值，则该变量转换为一个groups（superpositioning）变量。设置nlevels=0来防止这种行为。对于其他情况下，一个数字x轴变量nlevels或将导致更少的唯一值，而不是一个XY坐标图要绘制的散点图。
参数：nlines
If formula is given, you can set nlines to TRUE to convert the x-axis variable to a factor and then to an integer. Points are plotted at integer values on the x-axis but labeled with category levels. Points are connected by lines.
如果formula，你可以设置nlinesTRUEx轴的变量转换的一个因素，然后为整数。点被绘制在x-轴的整数值，但标记的分类级别。点由线条连接。
参数：addpanel
an additional panel function to call along with panel functions used for xYplot and Dotplot displays
额外的面板要调用的函数用于xYplot和Dotplot显示面板功能
参数：scat1d.opts
a list containing named elements that specifies parameters to scat1d when data is given. The col parameter is usually derived from other plotting information and not specified by the user.
参数指定一个列表，其中包含命名的元素scat1d：data。 col参数通常是来自从其他绘图信息的，而不是由用户指定的。
参数：...
extra arguments to pass to xYplot or Dotplot. Some useful ones are label.curves and abline. Set label.curves to FALSE to suppress labeling of separate curves. Default is TRUE, which causes labcurve to be invoked to place labels at positions where the curves are most separated, labeling each curve with the full curve label. Set label.curves to a list to specify options to labcurve, e.g., label.curves= list(method="arrow", cex=.8). These option names may be abbreviated in the usual way arguments are abbreviated. Use for example label.curves=list(keys=letters[1:5]) to draw single lower case letters on 5 curves where they are most separated, and automatically position a legend in the most empty part of the plot. The col, lty, and lwd parameters are passed automatically to labcurve although they may be overridden here.
额外的参数传递给xYplot或Dotplot。一些有用的是label.curves和abline。设置label.curves到FALSE抑制单独的曲线标签。默认是TRUE，它会导致labcurve被调用来放置标签的曲线最分离的位置处，与全曲线标签标记每条曲线。设置label.curves一个list指定选项来labcurve，例如，label.curves=list(method="arrow", cex=.8)的。这些选项的名称可能会用通常的方法参数的缩写简称。例如label.curves=list(keys=letters[1:5]) 5曲线相隔最远的地方，他们的画单个小写字母，并自动定位传说中最空的部分图。 col，lty和lwd参数自动传递到labcurve虽然他们可能在这里被覆盖。
参数：object
an object having a print method
一个一个print方法的对象
参数：y
y-coordinate for placing text in a lattice panel or on a base graphics plot
y坐标在lattice面板放置文本或图形的基础图
参数：cex
character expansion size for pantext
字符扩展的大小为pantext
参数：adj
text justification. Default is left justified.
文本对齐。默认是左对齐。
参数：fontfamily
font family for pantext. Default is "Courier" which will line up columns of a table.
字体家庭pantext。默认是"Courier"排队列的表。
参数：lattice
set to FALSE to use text instead of ltext in the function generated by pantext, to use base graphics
设置为FALSE使用text，而不是ltext中pantext，所产生的功能，使用基础的图形
Details
详细信息----------Details----------
When a groups (superpositioning) variable was used, you can issue the command Key(...) after printing the result of plot.Predict, to draw a key for the groups.
当一个groups（superpositioning）变量，你可以发出命令Key(...)印刷后的结果plot.Predict，，画出一个关键的群体。
值----------Value----------
a lattice object ready to print for rendering.
一个lattice对象准备print为渲染。
注意----------Note----------
If plotting the effects of all predictors you can reorder the panels using for example p <- Predict(fit); p$.predictor. <- factor(p$.predictor., v) where v is a vector of predictor names specified in the desired order.
如果绘制的所有预测变量的影响，你可以重新排列面板，例如使用p <- Predict(fit); p$.predictor. <- factor(p$.predictor., v)其中v是一个向量，预测所需的顺序在指定的名称。
（作者）----------Author(s)----------
Frank Harrell<br>
Department of Biostatistics, Vanderbilt University<br>
f.harrell@vanderbilt.edu
参考文献----------References----------
proportional-odds logit models: Extensions to the effects package. J Stat Software 32 No. 1.
参见----------See Also----------
Predict, rbind.Predict, datadist, predictrms, anova.rms, contrast.rms, summary.rms, rms, rmsMisc, labcurve, scat1d, xYplot, Overview
Predict，rbind.Predict，datadist，predictrms，anova.rms，contrast.rms，summary.rms，rms，<所述>，rmsMisc，labcurve，scat1d，xYplot
实例----------Examples----------
n <- 1000 # define sample size[确定样本量]
set.seed(17) # so can reproduce the results[所以可以重现的结果]
age <- rnorm(n, 50, 10)
blood.pressure <- rnorm(n, 120, 15)
cholesterol <- rnorm(n, 200, 25)
sex <- factor(sample(c('female','male'), n,TRUE))
label(age) <- 'Age' # label is in Hmisc[标签是在Hmisc]
label(cholesterol) <- 'Total Cholesterol'
label(blood.pressure) <- 'Systolic Blood Pressure'
label(sex) <- 'Sex'
units(cholesterol) <- 'mg/dl' # uses units.default in Hmisc[使用units.default在Hmisc]
units(blood.pressure) <- 'mmHg'
# Specify population model for log odds that Y=1[指定的log几率的人口模型Y = 1]
L <- .4*(sex=='male') + .045*(age-50) +
(log(cholesterol - 10)-5.2)*(-2*(sex=='female') + 2*(sex=='male'))
# Simulate binary y to have Prob(y=1) = 1/[1+exp(-L)][模拟二进制y以有PROB（y = 1时）= 1 / [1 +（-L）]]
y <- ifelse(runif(n) < plogis(L), 1, 0)
ddist <- datadist(age, blood.pressure, cholesterol, sex)
options(datadist='ddist')
fit <- lrm(y ~ blood.pressure + sex * (age + rcs(cholesterol,4)),
x=TRUE, y=TRUE)
plot(Predict(fit)) # Plot effects of all 4 predictors[图的所有的预测]
plot(Predict(fit), data=llist(blood.pressure,age))
# rug plot for two of the predictors[地毯图的预测]
p <- Predict(fit, name=c('age','cholesterol')) # Make 2 plots[制作2图]
plot(p)
p <- Predict(fit, age=seq(20,80,length=100), sex, conf.int=FALSE)
# Plot relationship between age and log[图年龄之间的关系和log]
# odds, separate curve for each sex,[赔率，每次性生活的单独的曲线，]
plot(p, subset=sex=='female' | age > 30)
# No confidence interval, suppress estimates for males <= 30[没有信心区间，抑制为男性<= 30的估计]
p <- Predict(fit, age, sex)
plot(p, label.curves=FALSE, data=llist(age,sex))
# use label.curves=list(keys=c('a','b'))'[使用label.curves =列表（键= C（A，B））]
# to use 1-letter abbreviations[使用1个字母的缩写]
# data= allows rug plots (1-dimensional scatterplots)[数据=允许地毯图（一维散点图）]
# on each sex's curve, with sex-[每次做爱的曲线上，与性别]
# specific density of age[年龄的特定密度]
# If data were in data frame could have used that[如果数据框的数据，也可以使用]
p <- Predict(fit, age=seq(20,80,length=100), sex='male', fun=plogis)
# works if datadist not used[如果不使用datadist工程]
plot(p, ylab=expression(hat(P)))
# plot predicted probability in place of log odds[图的预测概率在地方的log赔率]
per <- function(x, y) x >= 30
plot(p, perim=per) # suppress output for age < 30 but leave scale alone[抑制输出<30岁，但离开秤]
# Take charge of the plot setup by specifying a lattice formula[负责的图设置指定格公式]
p <- Predict(fit, age, blood.pressure=c(120,140,160),
cholesterol=c(180,200,215), sex)
plot(p, ~ age | blood.pressure*cholesterol, subset=sex=='male')
plot(p, ~ age | cholesterol*blood.pressure, subset=sex=='female')
plot(p, ~ blood.pressure|cholesterol*round(age,-1), subset=sex=='male')
plot(p)
# Plot the age effect as an odds ratio[绘制的年龄效应的比值比]
# comparing the age shown on the x-axis to age=30 years[比较上所示的x轴年龄= 30岁的年龄]
ddist$limits$age[2] <- 30 # make 30 the reference value for age[30的参考值年龄]
# Could also do: ddist$limits["Adjust to","age"] <- 30[也可以这样做：ddist $限制=“调整”，“年龄”] < - 30]
fit <- update(fit) # make new reference value take effect[新的参考值生效]
p <- Predict(fit, age, ref.zero=TRUE, fun=exp)
plot(p, ylab='Age=x:Age=30 Odds Ratio',
abline=list(list(h=1, lty=2, col=2), list(v=30, lty=2, col=2)))
# Compute predictions for three predictors, with superpositioning or[三年的预测，与superpositioning或计算预测]
# conditioning on sex, combined into one graph[空调性别，组合成一个图形]
p1 <- Predict(fit, age, sex)
p2 <- Predict(fit, cholesterol, sex)
p3 <- Predict(fit, blood.pressure, sex)
p <- rbind(age=p1, cholesterol=p2, blood.pressure=p3)
plot(p, groups='sex', varypred=TRUE, adj.subtitle=FALSE)
plot(p, cond='sex', varypred=TRUE, adj.subtitle=FALSE)
## Not run: [＃不运行：]
# For males at the median blood pressure and cholesterol, plot 3 types[对于男性的平均血压和胆固醇，积3种类型]
# of confidence intervals for the probability on one plot, for varying age[不同年龄的置信区间的概率在一个图，]
ages <- seq(20, 80, length=100)
p1 <- Predict(fit, age=ages, sex='male', fun=plogis) # standard pointwise[标准逐点]
p2 <- Predict(fit, age=ages, sex='male', fun=plogis,
conf.type='simultaneous') # simultaneous[同时]
p3 <- Predict(fit, age=c(60,65,70), sex='male', fun=plogis,
conf.type='simultaneous') # simultaneous 3 pts[同时3分]
# The previous only adjusts for a multiplicity of 3 points instead of 100[以前只有3个点的多重调整，而不是100]
f <- update(fit, x=TRUE, y=TRUE)
g <- bootcov(f, B=500, coef.reps=TRUE)
p4 <- Predict(g, age=ages, sex='male', fun=plogis) # bootstrap percentile[举个百分]
p <- rbind(Pointwise=p1, 'Simultaneous 100 ages'=p2,
'Simultaneous 3 ages'=p3, 'Bootstrap nonparametric'=p4)
xYplot(Cbind(yhat, lower, upper) ~ age, groups=.set.,
data=p, type='l', method='bands', label.curve=list(keys='lines'))
## End(Not run)[＃（不执行）]
# Plots for a parametric survival model[图参数生存模型]
n <- 1000
set.seed(731)
age <- 50 + 12*rnorm(n)
label(age) <- "Age"
sex <- factor(sample(c('Male','Female'), n,
rep=TRUE, prob=c(.6, .4)))
cens <- 15*runif(n)
h <- .02*exp(.04*(age-50)+.8*(sex=='Female'))
t <- -log(runif(n))/h
label(t) <- 'Follow-up Time'
e <- ifelse(t<=cens,1,0)
t <- pmin(t, cens)
units(t) <- "Year"
ddist <- datadist(age, sex)
Srv <- Surv(t,e)
# Fit log-normal survival model and plot median survival time vs. age[适合登录正常的生存模式和图中位生存时间与年龄]
f <- psm(Surv(t, e) ~ rcs(age), dist='lognormal')
med <- Quantile(f) # Creates function to compute quantiles[创建函数来计算位数]
# (median by default)[（默认情况下，中位数）]
p <- Predict(f, age, fun=function(x) med(lp=x))
plot(p, ylab="Median Survival Time")
# Note: confidence intervals from this method are approximate since[注意：这种方法的置信区间是近似的，因为]
# they don't take into account estimation of scale parameter[他们没有考虑到帐户估计尺度参数]
# Fit an ols model to log(y) and plot the relationship between x1[适合OLS模型进行登录（Y），并画出X1之间的关系]
# and the predicted mean(y) on the original scale without assuming[和预测的平均值（y）在原有规模没有假设]
# normality of residuals; use the smearing estimator[正常的残留物，使用涂抹估计]
# See help file for rbind.Predict for a method of showing two[显示两个方法，请参阅帮助文件rbind.Predict]
# types of confidence intervals simultaneously.[同时类型的置信区间。]
set.seed(1)
x1 <- runif(300)
x2 <- runif(300)
ddist <- datadist(x1,x2)
y <- exp(x1+x2-1+rnorm(300))
f <- ols(log(y) ~ pol(x1,2)+x2)
r <- resid(f)
smean <- function(yhat)smearingEst(yhat, exp, res, statistic='mean')
formals(smean) <- list(yhat=numeric(0), res=r[!is.na(r)])
#smean$res <- r[!is.na(r)] # define default res argument to function[smean $水库 - R [！is.na（R）]＃定义默认水库参数，功能]
plot(Predict(f, x1, fun=smean), ylab='Predicted Mean on y-scale')
# Make an 'interaction plot', forcing the x-axis variable to be[“互动图，迫使x轴变量]
# plotted at integer values but labeled with category levels[绘制整数值，但标有分类级别]
n <- 100
set.seed(1)
gender <- c(rep('male', n), rep('female',n))
m <- sample(c('a','b'), 2*n, TRUE)
d <- datadist(gender, m); options(datadist='d')
anxiety <- runif(2*n) + .2*(gender=='female') + .4*(gender=='female' & m=='b')
tapply(anxiety, llist(gender,m), mean)
f <- ols(anxiety ~ gender*m)
p <- Predict(f, gender, m)
plot(p) # horizontal dot chart; usually preferred for categorical predictors[通常是首选的分类预测的水平点图;]
Key(.5, .5)
plot(p, ~gender, groups='m', nlines=TRUE)
plot(p, ~m, groups='gender', nlines=TRUE)
plot(p, ~gender|m, nlines=TRUE)
options(datadist=NULL)
## Not run: [＃不运行：]
# Example in which separate curves are shown for 4 income values[例如，在不同的曲线如图4的收入值]
# For each curve the estimated percentage of voters voting for[每条曲线的估计百分比的选民投票]
# the democratic party is plotted against the percent of voters[％的选民对民主党绘制]
# who graduated from college. Data are county-level percents.[他们从大学毕业。资料县级百分比。]
incomes <- seq(22900, 32800, length=4)
# equally spaced to outer quintiles[同样间隔外的五分之一人口]
p <- Predict(f, college, income=incomes, conf.int=FALSE)
plot(p, xlim=c(0,35), ylim=c(30,55))
# Erase end portions of each curve where there are fewer than 10 counties having[清除端部有少于10个县，每一个曲线，]
# percent of college graduates to the left of the x-coordinate being plotted,[％的大学毕业生的x坐标左边的绘制，]
# for the subset of counties having median family income with 1650[家庭收入中位数1650个县的子集]
# of the target income for the curve[目标收入的曲线]
show.pts <- function(college.pts, income.pt) {
s <- abs(income - income.pt) < 1650 #assumes income known to top frame[假定收入顶部框架]
x <- college[s]
x <- sort(x[!is.na(x)])
n <- length(x)
low <- x[10]; high <- x[n-9]
college.pts >= low & college.pts <= high
}
plot(p, xlim=c(0,35), ylim=c(30,55), perim=show.pts)
## End(Not run)[＃（不执行）]
转载请注明:出自 生物统计家园网(http://www.biostatistic.net)。
注：
注1：为了方便大家学习，本文档为生物统计家园网机器人LoveR翻译而成，仅供个人R语言学习参考使用，生物统计家园保留版权。
注2：由于是机器人自动翻译，难免有不准确之处，使用时仔细对照中、英文内容进行反复理解，可以帮助R语言的学习。
注3：如遇到不准确之处，请在本贴的后面进行回帖，我们会逐渐进行修订。
|
发表于 2012-9-27 19:12:50
